Systems and methods for performing speech recognition

• US 20050267754A1
• Filed: 06/01/2004
• Published: 12/01/2005
• Est. Priority Date: 06/01/2004
• Status: Active Grant

• Current Assignee: Rakuten Group, Inc.
• Original Assignee: Verizon Business Global LLC (Verizon Communications Inc.)
• Inventors: Sartini, Robert A., Schultz, Paul T.
• Granted Patent: US 8,392,193 B2
• Time in Patent Office: Days
• US Class Current: 704/252
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates

Abstract

A method for performing speech recognition includes receiving a voice input and generating at least one possible result corresponding to the voice input. The method may also include calculating a value for the speech recognition result and comparing the calculated value to a particular portion of the speech recognition result. The method may further include retrieving information based on one or more factors associated with the voice input and using the retrieved information to determine a likelihood that the speech recognition result is correct.

Claims

1. A method for performing speech recognition, comprising:

receiving a voice input;

generating a speech recognition result based on the voice input;

calculating a value using the speech recognition result; and

comparing the calculated value to a portion of the speech recognition result.

2. The method of claim 1, wherein the portion of the speech recognition result represents a predetermined character position in the speech recognition result, the method further comprising:

determining a confidence value associated with the speech recognition result based on the comparing.

3. The method of claim 1, further comprising:

generating a plurality of speech recognition results based on the voice input;

calculating a value for each of the plurality of speech recognition results;

comparing each calculated value to a portion of the corresponding speech recognition result; and

determining a confidence value associated with each of the plurality of respective speech recognition results.

4. The method of claim 1, wherein the voice input represents a vehicle identification number and the comparing includes:

comparing the calculated value to a ninth character of the speech recognition result.

5. The method of claim 1, further comprising:

receiving a telephone call from a user;

determining a telephone number from which the telephone call was made; and

retrieving information associated with the telephone number.

6. The method of claim 5, further comprising:

comparing the speech recognition result to the retrieved information; and

increasing a confidence value associated with the speech recognition result when the speech recognition result matches the retrieved information.

7. The method of claim 5, wherein the generating a speech recognition result comprises:

using the retrieved information to generate the speech recognition result.

8. The method of claim 1, further comprising:

providing a first prompt for information to a caller; and

receiving first information from the caller in response to the first prompt, wherein the generating a speech recognition result includes;

using the first information to select at least one rule associated with performing speech recognition on the voice input.

9. The method of claim 8, further comprising:

providing a second prompt for information to the caller; and

receiving second information from the caller in response to the second prompt, wherein the generating a speech recognition result includes;

using the second information to select at least one other rule associated with performing speech recognition on the voice input.

10. The method of claim 1, further comprising:

storing a plurality of rules associated with performing speech recognition on the voice input, at least some of the plurality of rules being based on constraints associated with a subject of the voice input.

11. A system, comprising:

a memory configured to store a plurality of rules associated with performing speech recognition, at least a portion of the rules being based on constraints associated with a type of information for which the speech recognition is to be performed; and

at least one logic device configured to;

receive a voice input, and

generate at least one speech recognition result based on the voice input using rules stored in the memory.

12. The system of claim 11, wherein the at least one logic device is further configured to:

calculate a value for the speech recognition result, and

compare the calculated value to a portion of the speech recognition result.

13. The system of claim 12, wherein the at least one logic device is further configured to:

determine that the at least one speech recognition results is a potentially correct speech recognition result when the calculated value matches the portion of the speech recognition result.

14. The system of claim 11, wherein the memory is further configured to store the plurality of rules based on a plurality of predetermined constraints associated with the type of information for which the speech recognition is to be performed.

15. The system of claim 11, wherein the at least one logic device is further configured to:

provide a first prompt to a user, and

receive first information in response to the first prompt, wherein the generating at least one speech recognition result includes;

using the first information to select at least one of the plurality of rules associated with performing speech recognition on the voice input.

16. The system of claim 15, wherein the at least one logic device is further configured to:

provide a second prompt to the user, and

receive second information in response to the second prompt, wherein the generating at least one speech recognition result further includes;

using the second information to at select at least one other rule associated with performing speech recognition on the voice input.

17. The system of claim 11, wherein the generating at least one speech recognition results comprises generating a plurality of speech recognition results, each of the plurality of speech recognition results representing a potentially correct speech recognition result.

18. The system of claim 17, wherein the at least one logic device is further configured to:

weight each of the plurality of speech recognition results, and identify one of the plurality of speech recognition as having a highest likelihood of correctly corresponding to the voice input based on the weighting.

19. The system of claim 11, further comprising:

an input device configured to receive a telephone call, wherein the at least one logic device is further configured to;

determine a telephone number from which the telephone call was made, and

retrieve information based on the telephone number.

20. The system of claim 19, wherein the at least one logic device is further configured to:

compare the retrieved information to the at least one speech recognition result.

21. A computer-readable medium having stored thereon a plurality of sequences of instructions, said sequences of instructions including instructions which, when executed by a processor, cause said processor to:

generate a speech recognition result based on a voice input;

calculate a value using at least a portion of the speech recognition result; and

determine whether the speech recognition result is incorrect using the calculated value.

22. The computer-readable medium of claim 21, wherein when determining whether the speech recognition result is incorrect, the instructions cause the processor to:

compare the calculated value to a portion of the speech recognition result, and

determine whether the speech recognition result is incorrect based on the comparing.

23. The computer-readable medium of claim 21, including instructions for further causing the processor to:

generate a plurality of speech recognition results, each of the plurality of speech recognition results potentially corresponding to the voice input; and

weight the plurality of speech recognition results.

24. The computer-readable medium of claim 21, including instructions for further causing the processor to:

retrieve information based on at least one of a telephone number of a caller or a name associated with the caller; and

compare the retrieved information to the speech recognition result.

25. A method, comprising:

receiving a telephone call from a user;

retrieving information based on a telephone number from which the telephone call was placed;

receiving a voice input from the caller; and

generating a speech recognition result based on the voice input.

26. The method of claim 25, further comprising:

comparing the retrieved information to the speech recognition result; and

determining a likelihood that the speech recognition result is correct based on the comparing.

27. The method of claim 25, further comprising:

performing a mathematical operation on the speech recognition result; and

comparing a result of the mathematical operation to a portion of the speech recognition result.

28. The method of claim 27, further comprising:

determining that the speech recognition result is incorrect when the result of the mathematical operation does not match the portion of the speech recognition result.

29. The method of claim 25, further comprising:

storing a plurality of rules associated with performing speech recognition on the voice input, at least some of the plurality of rules being based on constraints associated with a type of information for which the speech recognition is to be performed.

30. The method of claim 25, further comprising:

generating a plurality of speech recognition results;

weighting each of the plurality of speech recognition results; and

selecting one of the plurality of speech recognition results as corresponding to the voice input based on the weighting.